© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2546
    Prev
    Next
    INDEX
    Explanations

    back against, back adjusted, backstroke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lite
    -0.23
    ajo
    -0.22
    ä¸įäºĨ
    -0.22
    ä½łçļĦ
    -0.21
    éĨĭ
    -0.21
    åIJĪä¸Ģ
    -0.21
    -categories
    -0.20
     Cli
    -0.20
    ">'.$
    -0.20
    æ£Ĵ
    -0.20
    POSITIVE LOGITS
    zelf
    0.26
    å·¥ç¨ĭæľºæ¢°
    0.23
     superv
    0.22
     unthinkable
    0.21
    edo
    0.21
    æ±²
    0.21
    éĢıæĺİ
    0.21
    ç¯ĩ
    0.21
    bbc
    0.20
     neighbours
    0.20
    Activations Density 0.003%

    No Known Activations